Detail Across Scales: Multi-Scale Enhancement for Full Spectrum Neural Representations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908546634874880 |
|---|---|
| author | Ni, Yuan Chen, Zhantao Peng, Cheng Plumley, Rajan Yoon, Chun Hong Thayer, Jana B. Turner, Joshua J. |
| author_facet | Ni, Yuan Chen, Zhantao Peng, Cheng Plumley, Rajan Yoon, Chun Hong Thayer, Jana B. Turner, Joshua J. |
| contents | Implicit neural representations (INRs) have emerged as a compact and parametric alternative to discrete array-based data representations, encoding information directly in neural network weights to enable resolution-independent representation and memory efficiency. However, existing INR approaches, when constrained to compact network sizes, struggle to faithfully represent the multi-scale structures, high-frequency information, and fine textures that characterize the majority of scientific datasets. To address this limitation, we propose WIEN-INR, a wavelet-informed implicit neural representation that distributes modeling across different resolution scales and employs a specialized kernel network at the finest scale to recover subtle details. This multi-scale architecture allows for the use of smaller networks to retain the full spectrum of information while preserving the training efficiency and reducing storage cost. Through extensive experiments on diverse scientific datasets spanning different scales and structural complexities, WIEN-INR achieves superior reconstruction fidelity while maintaining a compact model size. These results demonstrate WIEN-INR as a practical neural representation framework for high-fidelity scientific data encoding, extending the applicability of INRs to domains where efficient preservation of fine detail is essential. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15494 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Detail Across Scales: Multi-Scale Enhancement for Full Spectrum Neural Representations Ni, Yuan Chen, Zhantao Peng, Cheng Plumley, Rajan Yoon, Chun Hong Thayer, Jana B. Turner, Joshua J. Machine Learning Data Analysis, Statistics and Probability Implicit neural representations (INRs) have emerged as a compact and parametric alternative to discrete array-based data representations, encoding information directly in neural network weights to enable resolution-independent representation and memory efficiency. However, existing INR approaches, when constrained to compact network sizes, struggle to faithfully represent the multi-scale structures, high-frequency information, and fine textures that characterize the majority of scientific datasets. To address this limitation, we propose WIEN-INR, a wavelet-informed implicit neural representation that distributes modeling across different resolution scales and employs a specialized kernel network at the finest scale to recover subtle details. This multi-scale architecture allows for the use of smaller networks to retain the full spectrum of information while preserving the training efficiency and reducing storage cost. Through extensive experiments on diverse scientific datasets spanning different scales and structural complexities, WIEN-INR achieves superior reconstruction fidelity while maintaining a compact model size. These results demonstrate WIEN-INR as a practical neural representation framework for high-fidelity scientific data encoding, extending the applicability of INRs to domains where efficient preservation of fine detail is essential. |
| title | Detail Across Scales: Multi-Scale Enhancement for Full Spectrum Neural Representations |
| topic | Machine Learning Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2509.15494 |